{"id":"W3087412484","doi":"10.1101/2020.09.18.292680","title":"LiftPose3D, a deep learning-based approach for transforming 2D to 3D pose in laboratory animals","year":2020,"lang":"en","type":"preprint","venue":"bioRxiv (Cold Spring Harbor Laboratory)","topic":"Advanced Vision and Imaging","field":"Computer Science","cited_by":16,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of British Columbia Hospital","funders":"","keywords":"Triangulation; Artificial intelligence; Computer vision; Computer science; Pose; Calibration; Kinematics; Camera resectioning; Deep learning; Macaque; Single camera; Mathematics; Geography; Psychology; Cartography; Neuroscience","routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005678445,0.00130402,0.0005575694,0.0007430345,0.0003082578,0.0007689214,0.001948066,0.001045512,0.004910491],"category_scores_gemma":[0.001324947,0.0007967186,0.00134522,0.0003651593,0.0009239272,0.0007683024,0.002373572,0.002173896,0.001619925],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0006236424,"about_ca_system_score_gemma":0.001180297,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00461038,"about_ca_topic_score_gemma":0.01141985,"domain_scores_codex":[0.9996433,0.00005665997,0.00001127011,0.0001206687,0.0001331534,0.0000348696],"domain_scores_gemma":[0.9997151,0.00008099266,0.00004248549,0.00008109012,0.0000402207,0.00004016251],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0003654459,0.0001912953,0.003589137,0.0003520164,0.0003422328,0.0003723712,0.0002030911,0.3661126,0.1016087,0.01243892,0.02364851,0.4907757],"study_design_scores_gemma":[0.00002741417,0.00008414497,0.0009423677,0.00003648437,0.00002182841,0.0001909496,0.00002966337,0.964165,0.01745135,0.009491435,0.00752926,0.00003007481],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.004779146,0.00009678918,0.9873614,0.00007724033,0.0000437261,0.00004746736,0.0005222314,0.006290002,0.0007818809],"genre_scores_gemma":[0.121907,0.000333975,0.8683254,0.000373297,0.00004414834,0.0003766574,0.002924511,0.001444494,0.004270518],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.004910491,"threshold_uncertainty_score":0.01642728,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01812446200043053,"score_gpt":0.2478394158025659,"score_spread":0.2297149538021354,"validation_status":"score_only:v0-immature-baseline","note":"Baseline scores from an immature model (maturity gate not passed). Scores rank; they never assert a category."}}